{"id":"W2747874407","doi":"10.21437/interspeech.2017-1386","title":"Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":1124,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Speech recognition; Natural language processing; Linguistics; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001516595,0.00277767,0.001390084,0.001683278,0.001093761,0.001602286,0.002982689,0.001746311,0.04015575],"category_scores_gemma":[0.003513813,0.001203066,0.0009146577,0.001191386,0.0005380725,0.001834674,0.002860261,0.002815411,0.03271436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001230704,"about_ca_system_score_gemma":0.002998003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02495923,"about_ca_topic_score_gemma":0.07083222,"domain_scores_codex":[0.9987844,0.0001771878,0.00007479649,0.0005425241,0.0002748267,0.000146321],"domain_scores_gemma":[0.9990196,0.0002922169,0.00004745299,0.000250816,0.0003099108,0.000080104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009877695,0.0001402019,0.0009038033,0.0004361517,0.0002449155,0.0003274812,0.0001405382,0.01511038,0.06774936,0.004793619,0.09338108,0.8157847],"study_design_scores_gemma":[0.0003450229,0.0004149374,0.00299967,0.00007115441,0.0001696539,0.0004948851,0.0001874056,0.6596141,0.2119787,0.007671501,0.1158386,0.0002143595],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006596823,0.0007776082,0.8189954,0.0001815179,0.0005664086,0.0002779907,0.00539089,0.1621147,0.00509851],"genre_scores_gemma":[0.0815911,0.0004052924,0.8635892,0.0004231085,0.00013866,0.0006317325,0.02319972,0.008349862,0.02167131],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.04015575,"threshold_uncertainty_score":0.1343343,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04401314992965729,"score_gpt":0.2826153983171813,"score_spread":0.238602248387524,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}